ml-agents

作者	SHA1	备注	提交日期
Hunter-Unity	f4c8f344	2e7 steps	5 年前
Hunter-Unity	07266f46	add dir vector obsv	5 年前
Hunter-Unity	c9821f85	100M steps	5 年前
Hunter-Unity	99eadde6	try 100M steps on walkerdynamic	5 年前
Hunter-Unity	9add4a97	increase gravity to 1.5	5 年前
Hunter-Unity	1316aa98	iterate through list not dict to collect observations	5 年前
Hunter-Unity	da6d25c9	updated walker dynamic demo file. cleanup	5 年前
Hunter-Unity	10f12c25	cleanup	5 年前
Hunter-Unity	12cbca77	updated WalkerStatic scene with new ragdoll	5 年前
Hunter-Unity	6e0dbc22	cleanup	5 年前
Hunter-Unity	89e95781	clean up	5 年前
GitHub	e724a8ad	ObservableAttribute - use dictionary for sensor type too (#3978 ) * use dictionary for sensortype too * update comment	5 年前
Hunter-Unity	81e976ac	added dirIndicator and orentCubeGizmo	5 年前
GitHub	197cf3e7	ObservableAttribute (#3925 ) * ObservableAttribute proof-of-concept * restructue sensors, add int impl, unit test * add vector3 sensor, cleanup constructors * add more types * account for observables in barracuda checks * iterators for observable fields/props * stacking, fix obs size in prefab * use DeclaredOnly to filter members * ignore write-only properties * fix error message * docstrings * agent enum (WIP) * agent enum and unit tests * fix comment * cleanup TODO * ignore by default, rename declaredOnly param, docstrings * fix tests * rename, cleanup, revert FoodCollector * warning for write-only, no exception for invalid type * move observableAttributeHandling to BehaviorParameters * autoformatting * changelog * fix up sensor creation logic	5 年前
Hunter-Unity	7b35627d	about to clean up code	5 年前
GitHub	f26c2b3a	Add needed indent to fix config file (#3968 )	5 年前
Hunter-Unity	d29cc962	fix hip rotation	5 年前
GitHub	c1f010ef	Develop mm fix readme releases (#3966 ) * Fix broken link and clean-up Releases section. * Updated link to be consistent with the table. * Update one of the bullets for consistency.	5 年前
Hunter-Unity	cb8eec30	Create WalkerDynamic.yaml	5 年前
GitHub	96ddb1b9	Docs: remove --curriculum flag (#3921 )	5 年前
Hunter-Unity	9e20feef	hip facing reward	5 年前
GitHub	abbc6424	[bug-fix] Fix issue with initialize not resetting step count (#3962 )	5 年前
Hunter-Unity	0b02b434	added new dynamic nn file	5 年前
GitHub	3a8f6d0c	Adding some tests (#3952 ) * Adding some tests * fixing the step test by enforcing the types of np.array * addressing comments	5 年前
Hunter-Unity	e037175e	collect local rotations	5 年前
GitHub	8bae4088	Develop better error message for #3953 (#3963 ) * Making the error for wrong number of agents raise consistently * Better error message for inputs of wrong dimensions	5 年前
Hunter-Unity	5f149660	DynamicWalker working. has working nn file	5 年前
GitHub	9083752d	Making some things private in UnityEnvironment (#3951 ) * Making some things private in UnityEnvironment * Readding the default ports as public * removing _SCALAR_ACTION_TYPES and _SINGLE_BRAIN_ACTION_TYPES * Removing unused method	5 年前
Hunter-Unity	c4943a05	added dynamic walker tf file. max speed 5	5 年前
GitHub	e274bcf6	Update precommit flake8 (#3961 ) * fix flake8 errors * update flake8 hook * update flake8 plugins	5 年前
Hunter-Unity	78256e86	updated dynamic platforms	5 年前
GitHub	0f5d79ca	Fix #3932 , stop the editor from going into a loop when a prefab is selected. (#3949 )	5 年前
Hunter-Unity	6f91aeae	added trained model, renamed scene, usecollisioncallbacks	5 年前
GitHub	c6ed3789	Replaced get_behavior_names and get_behavior_spec with behavior_specs property (#3946 ) * Replaced get_behavior_names and get_behavior_spec with behavior_specs property * Fixing the test * [ci] * addressing some comments * use typing.Mapping (#3948) * Update ml-agents-envs/mlagents_envs/base_env.py Co-authored-by: Chris Elion <chris.elion@unity3d.com> * Adding the documentation Co-authored-by: Chris Elion <chris.elion@unity3d.com>	5 年前
Hunter-Unity	b1e5a6f8	fixed bp heirarchy	5 年前
GitHub	69fa337d	Update issue templates (#3950 ) Co-authored-by: Chris Elion <chris.elion@unity3d.com>	5 年前
Hunter-Unity	bfb4eddc	update walker pair prefab	5 年前
GitHub	2b207401	Add v1.0 blog post and update reference paper. (#3947 )	5 年前
Hunter-Unity	182aaee3	rebuilt ragdoll ready	5 年前
GitHub	96dc2545	[docs] Fix a configuration error in RollerBall that doesn't allow training to run. (#3945 ) mlagents.trainers.exception.UnityTrainerException: The hyper-parameter memory_size could not be found for the <class 'mlagents.trainers.ppo.trainer.PPOTrainer'> trainer of brain RollerBall.	5 年前
Hunter-Unity	546c610f	rebuilt walker ragdoll to scale 1	5 年前
Andrew Cohen	099685fe	removed stop gradient/add trainable=false	5 年前
GitHub	812983c0	Some improvements to the UnityEnvironment class (#3939 ) * Fix typo * Made a side channel utils to reduce the complexity of UnityEnvironment * Added a get_side_channel_dict utils method * Better executable launcher (unarguably) * Fixing the broken test * Addressing comments * [skip ci] Update ml-agents-envs/mlagents_envs/side_channel/side_channel_manager.py Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com> * No catch all Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com>	5 年前
Hunter-Unity	3edca8d0	reduced maxAngVel, enabled enhanced determinism, cont spec	5 年前
Andrew Cohen	f1817661	update change log	5 年前
GitHub	c5b94ca6	Use LR schedule for beta and epsilon (#3940 )	5 年前
Hunter-Unity	56a22426	removed texture example	5 年前
Andrew Cohen	4a3ad193	Add constant decay to beta and epsilon	5 年前
GitHub	e449d1a7	[docs] Add more context for interacting with an environment. (#3938 )	5 年前
Hunter-Unity	9d46b450	increased joint strength to 40k	5 年前

1 2

75 次代码提交 (f4c8f344-a962-4949-b223-8a3e69fc6877)